{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AODJQC2OQZHMGI6H5Z3LBT4KIC","short_pith_number":"pith:AODJQC2O","schema_version":"1.0","canonical_sha256":"0386980b4e864ec323c7ee76b0cf8a408c732a2c56b16eee858da99be458c7a1","source":{"kind":"arxiv","id":"2311.17137","version":3},"attestation_state":"computed","paper":{"title":"Generative Models: What Do They Know? Do They Know Things? Let's Find Out!","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anand Bhattad, Greg Shakhnarovich, Nicholas Kolkin, Xiaodan Du","submitted_at":"2023-11-28T18:59:02Z","abstract_excerpt":"Generative models excel at mimicking real scenes, suggesting they might inherently encode important intrinsic scene properties. In this paper, we aim to explore the following key questions: (1) What intrinsic knowledge do generative models like GANs, Autoregressive models, and Diffusion models encode? (2) Can we establish a general framework to recover intrinsic representations from these models, regardless of their architecture or model type? (3) How minimal can the required learnable parameters and labeled data be to successfully recover this knowledge? (4) Is there a direct link between the"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2311.17137","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-28T18:59:02Z","cross_cats_sorted":["cs.AI","cs.GR","cs.LG"],"title_canon_sha256":"d0269a54dc2bee43b85a20bd64c4621383870151cb8ff6aaa5901b108eb8f4da","abstract_canon_sha256":"9a1ee8a7045cf75217c6274915d4c16e53238b50df6290660d0d170843d3d95a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:01.636995Z","signature_b64":"yxi2zeCCFsaOI+cjcP48N3uPMdqgrnCsfpeJuSMotlf+ldviUeBeAfzge2pelqjYRx2JPTj26D8OwjYhjNTeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0386980b4e864ec323c7ee76b0cf8a408c732a2c56b16eee858da99be458c7a1","last_reissued_at":"2026-07-05T09:21:01.636393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:01.636393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Models: What Do They Know? Do They Know Things? Let's Find Out!","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anand Bhattad, Greg Shakhnarovich, Nicholas Kolkin, Xiaodan Du","submitted_at":"2023-11-28T18:59:02Z","abstract_excerpt":"Generative models excel at mimicking real scenes, suggesting they might inherently encode important intrinsic scene properties. In this paper, we aim to explore the following key questions: (1) What intrinsic knowledge do generative models like GANs, Autoregressive models, and Diffusion models encode? (2) Can we establish a general framework to recover intrinsic representations from these models, regardless of their architecture or model type? (3) How minimal can the required learnable parameters and labeled data be to successfully recover this knowledge? (4) Is there a direct link between the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17137","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.17137/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.17137","created_at":"2026-07-05T09:21:01.636468+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.17137v3","created_at":"2026-07-05T09:21:01.636468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17137","created_at":"2026-07-05T09:21:01.636468+00:00"},{"alias_kind":"pith_short_12","alias_value":"AODJQC2OQZHM","created_at":"2026-07-05T09:21:01.636468+00:00"},{"alias_kind":"pith_short_16","alias_value":"AODJQC2OQZHMGI6H","created_at":"2026-07-05T09:21:01.636468+00:00"},{"alias_kind":"pith_short_8","alias_value":"AODJQC2O","created_at":"2026-07-05T09:21:01.636468+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.14461","citing_title":"Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Rendering","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AODJQC2OQZHMGI6H5Z3LBT4KIC","json":"https://pith.science/pith/AODJQC2OQZHMGI6H5Z3LBT4KIC.json","graph_json":"https://pith.science/api/pith-number/AODJQC2OQZHMGI6H5Z3LBT4KIC/graph.json","events_json":"https://pith.science/api/pith-number/AODJQC2OQZHMGI6H5Z3LBT4KIC/events.json","paper":"https://pith.science/paper/AODJQC2O"},"agent_actions":{"view_html":"https://pith.science/pith/AODJQC2OQZHMGI6H5Z3LBT4KIC","download_json":"https://pith.science/pith/AODJQC2OQZHMGI6H5Z3LBT4KIC.json","view_paper":"https://pith.science/paper/AODJQC2O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.17137&json=true","fetch_graph":"https://pith.science/api/pith-number/AODJQC2OQZHMGI6H5Z3LBT4KIC/graph.json","fetch_events":"https://pith.science/api/pith-number/AODJQC2OQZHMGI6H5Z3LBT4KIC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AODJQC2OQZHMGI6H5Z3LBT4KIC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AODJQC2OQZHMGI6H5Z3LBT4KIC/action/storage_attestation","attest_author":"https://pith.science/pith/AODJQC2OQZHMGI6H5Z3LBT4KIC/action/author_attestation","sign_citation":"https://pith.science/pith/AODJQC2OQZHMGI6H5Z3LBT4KIC/action/citation_signature","submit_replication":"https://pith.science/pith/AODJQC2OQZHMGI6H5Z3LBT4KIC/action/replication_record"}},"created_at":"2026-07-05T09:21:01.636468+00:00","updated_at":"2026-07-05T09:21:01.636468+00:00"}